Implementing TD3 to train a Neural Network to fly a Quadcopter through an FPV Gate
This work addresses autonomous drone navigation for robotics applications, but it is incremental as it applies an existing method to a specific task.
The paper tackled the problem of training a quadcopter to fly through a gate using deep reinforcement learning, specifically applying the TD3 algorithm to develop a velocity controller, and demonstrated successful real-world deployment in a laboratory environment.
Deep Reinforcement learning has shown to be a powerful tool for developing policies in environments where an optimal solution is unclear. In this paper, we attempt to apply Twin Delayed Deep Deterministic Policy Gradients to train a neural network to act as a velocity controller for a quadcopter. The quadcopter's objective is to quickly fly through a gate while avoiding crashing into the gate. We transfer our trained policy to the real world by deploying it on a quadcopter in a laboratory environment. Finally, we demonstrate that the trained policy is able to navigate the drone to the gate in the real world.